CN113160807A - Corpus updating method and system and voice control equipment - Google Patents
Corpus updating method and system and voice control equipment Download PDFInfo
- Publication number
- CN113160807A CN113160807A CN202010073090.2A CN202010073090A CN113160807A CN 113160807 A CN113160807 A CN 113160807A CN 202010073090 A CN202010073090 A CN 202010073090A CN 113160807 A CN113160807 A CN 113160807A
- Authority
- CN
- China
- Prior art keywords
- corpus
- voice
- information
- default
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000009471 action Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 20
- 238000012217 deletion Methods 0.000 claims description 18
- 230000037430 deletion Effects 0.000 claims description 18
- 230000004048 modification Effects 0.000 claims description 16
- 238000012986 modification Methods 0.000 claims description 16
- 238000012790 confirmation Methods 0.000 claims description 11
- 238000004378 air conditioning Methods 0.000 description 15
- 239000000463 material Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Abstract
The invention relates to a corpus updating method, a corpus updating system and voice control equipment, wherein the method comprises the following steps: acquiring a voice instruction input by a user, and acquiring a voice text according to the voice instruction; recognizing the voice text, and if the voice text cannot be recognized, outputting prompt information for requesting a user to perform action teaching; acquiring a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time. By implementing the method and the device, the continuous increase of the corpus corpora of the personalized corpus based on the user can be realized.
Description
Technical Field
The invention relates to the technical field of word sense information processing, in particular to a corpus updating method and system and voice control equipment.
Background
The corpus is a structured, representative, computer-searchable corpus of a scale specifically collected for one or more application targets. The corpus is usually obtained from an open corpus data set, a crawler technology and an own platform, and therefore, the new expansion of the corpus is basically performed in the background and is generally discontinuous. The general voice control device only has the right of use for the end user, but does not have the personalized corpus dynamic expansion function.
In the process of implementing the invention, the inventor finds that the prior art has at least the following technical problems: the method for increasing the corpus or upgrading the corpus by the existing speech recognition system is usually based on big data, training and upgrading are carried out on a background, unconventional and personalized phrases are generally cleaned, and the method does not support the local increase of users.
Disclosure of Invention
The invention aims to provide a corpus updating method, a corpus updating system and voice control equipment so as to realize continuous new corpus corpora based on user personalized data.
In a first aspect, an embodiment of the present invention provides a method for updating a corpus, including:
step S1, acquiring a voice instruction input by a user, and acquiring a voice text according to the voice instruction;
step S2, recognizing the voice text, and if the voice text cannot be recognized, outputting first prompt information for requesting a user to perform action teaching;
step S3, acquiring a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time.
Preferably, recognizing the phonetic text comprises:
and searching whether the corpus is provided with the corpus corresponding to the voice text or not, if so, successfully identifying, and if not, identifying.
Preferably, the step S2 includes:
if the voice text is successfully identified, generating a task instruction and a broadcast instruction according to the searched corpus corresponding to the voice text, wherein the task instruction is used for controlling the execution unit to execute a corresponding task, and the broadcast instruction is used for controlling the broadcast unit to broadcast the content corresponding to the corpus.
Preferably, the step S3 includes:
after the first prompt message is output, receiving a teaching ending voice command input by a user within preset time;
when a teaching end voice instruction input by a user is received, acquiring task operation information in a time period from the time when the first prompt information is output to the time when the teaching end voice instruction is input by the user;
acquiring a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus.
Preferably, the method includes acquiring a plurality of default corpora corresponding to the task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus, and specifically includes:
acquiring a plurality of default corpora corresponding to the task operation information; the task operation information comprises operation information of a plurality of tasks, and each task corresponds to a default corpus;
outputting second prompt information according to the default corpora, wherein the second prompt information is used for requesting a user to confirm whether the default corpora are consistent with the voice text;
after the second prompt message is output, if confirmation information input by a user is received, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus.
Preferably, the method further comprises:
determining a task corresponding to each corpus according to a plurality of corpora of the corpus and a corpus relation between the corpora;
generating display information according to the task corresponding to each corpus, and sending the display information to a display unit; the display unit is used for displaying the display information.
Preferably, the method further comprises:
obtaining corpus modification information or corpus deletion information input by a user;
and modifying the corpus and/or the corpus relation in the corpus according to the corpus modification information, or deleting the corpus and/or the corpus relation in the corpus according to the corpus deletion information.
In a second aspect, an embodiment of the present invention provides a corpus updating system, including:
the information acquisition unit is used for acquiring a voice instruction input by a user and acquiring a voice text according to the voice instruction;
the recognition processing unit is used for recognizing the voice text, and if the voice text cannot be recognized, outputting first prompt information for requesting a user to perform action teaching; and
the corpus updating unit is used for acquiring a plurality of default corpuses corresponding to the task operation information, establishing a corpus relation between the default corpuses and the voice text, and storing the voice text as a new corpus and the corpus relation into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time.
Preferably, the corpus updating unit includes:
the first updating processing unit is used for receiving a teaching ending voice instruction input by a user within preset time after outputting the first prompt message;
the second updating processing unit is used for acquiring task operation information in a time period from the time when the first prompt information is output to the time when the teaching ending voice instruction input by the user is received; and
and the third updating processing unit is used for acquiring a plurality of default corpora corresponding to the task operation information, establishing a corpus relation between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relation into a corpus.
Preferably, the third update processing unit includes:
the default corpus acquiring unit is used for acquiring a plurality of default corpora corresponding to the task operation information; the task operation information comprises operation information of a plurality of tasks, and each task corresponds to a default corpus;
the corpus confirmation prompting unit is used for outputting second prompting information according to the default corpuses, and the second prompting information is used for requesting a user to confirm whether the default corpuses are consistent with the voice text; and
and the corpus increasing unit is used for establishing a corpus relation between the default corpora and the voice text after the second prompt information is output and if confirmation information input by a user is received, and storing the voice text serving as a new corpus and the corpus relation into a corpus.
Preferably, the system further comprises:
the determining unit is used for determining a task corresponding to each corpus according to the corpus relations among the corpora and the corpora of the corpus;
the display information generating unit is used for generating display information according to the task corresponding to each corpus and sending the display information to the display unit; the display unit is used for displaying the display information.
Preferably, the system further comprises:
a deletion information acquisition unit for acquiring corpus modification information or corpus deletion information input by a user;
and the deleting processing unit is used for modifying the corpus and/or the corpus relation in the corpus according to the corpus modification information, or deleting the corpus and/or the corpus relation in the corpus according to the corpus deletion information.
In a third aspect, an embodiment of the present invention provides a voice control apparatus, including: the corpus updating system according to the embodiment of the invention; or a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the corpus update method according to the embodiment of the present invention.
Compared with the prior art, the technical scheme has the following beneficial effects: when a corpus is updated, a corpus to be newly added to the corpus is required to be acquired, namely a voice text input by a user, semantic information processing is carried out on the voice text, the voice text is identified, and if the voice text cannot be identified, first prompt information for requesting the user to carry out action teaching is output; after the user obtains the prompt of the first prompt message, the manual operation execution unit executes the corresponding task, and the execution unit generates task operation information in the process of executing the task, namely, the task operation information indicates which tasks are executed; further, a plurality of default corpora corresponding to the task operation information are obtained, and after a corpus relation is established between the default corpora and the voice text, the voice text is used as a new corpus and is stored in a corpus together with the corpus relation. Through adopting the mode that user manual operation carries out the teaching, self-defining is carried out to newly-increased corpus, realizes that the corpus based on user's individualized data lasts newly-increased.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart illustrating a corpus updating method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a corpus updating system according to a second embodiment of the present invention.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, well known means have not been described in detail so as not to obscure the present invention.
An embodiment of the present invention provides a corpus updating method, which can be applied to a vehicle-mounted voice assistant, fig. 1 is a flowchart of the corpus updating method according to this embodiment, and referring to fig. 1, the method according to this embodiment includes the following steps S101 to S103:
s101, acquiring a voice instruction input by a user, and acquiring a voice text according to the voice instruction;
for example, a user may input a voice command through a microphone, and in the step, the voice command input by the user may be processed and converted into a voice text by using an Automatic Speech Recognition (ASR) system, and the voice text that has been successfully converted may be obtained through a corresponding interface.
Step S102, recognizing the voice text, and if the voice text cannot be recognized, outputting first prompt information for requesting a user to perform action teaching;
specifically, in the step, the voice text is processed by an NPL engine (Natural Language Processing). When the NPL engine cannot recognize the speech text, it indicates that there is no corpus corresponding to the speech text in the corpus, that is, the speech instruction is an undefined instruction. At this time, entering an incremental learning process of the corpus, and outputting first prompt information for requesting a user to perform action teaching, wherein the first prompt information is, for example, "the question is still unknown, and please teach me". For example, the prompting mode of the first prompting message may be a voice mode and/or a mode that a display unit displays.
Step S103, acquiring a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time.
Specifically, after obtaining the prompt of the first prompt information, the user performs manual operation on the corresponding execution unit within a preset time, that is, completes teaching, and in the manual operation process, the task operation information can be obtained according to the task operation condition of the corresponding execution unit. According to the task operation information, a plurality of default corpora corresponding to the task operation information can be determined; the default corpus refers to a corpus stored in a corpus, which is a non-user-defined corpus, namely, updated corpus is downloaded from a background database; further, after establishing the corpus relationship between the default corpora and the voice text, storing the voice text as a new corpus and the corpus relationship into a corpus.
Therefore, the method of the embodiment can customize the newly added corpus by adopting a mode of teaching by manual operation of a user, and can realize continuous addition of the corpus based on personalized data of the user.
Illustratively, the corpus in this embodiment includes a default corpus and a dynamic corpus, the default corpus is used to store a plurality of default corpora, the dynamic corpus is used to store user-defined corpora, such as a new corpus defined by the user for teaching, and in addition, a table or other forms representing relationships between corpora are also stored in the corpus.
In a specific embodiment, recognizing the phonetic text includes:
the NPL engine searches whether the corpus is provided with the corpus corresponding to the voice text or not, if the corpus is provided with the corpus corresponding to the voice text, the recognition is successful, and if the corpus is not provided with the corpus corresponding to the voice text, the recognition cannot be performed.
For example, in a vehicle-mounted scene, a user issues a voice command of "open air conditioning", and only the corpus of "open air conditioning" is stored in the corpus, so that "open air conditioning" cannot be recognized.
For another example, in a vehicle-mounted scene, a user issues a voice command of "turn on the air conditioner", and the corpus stores the corpus of "turn on the air conditioner", so that the user can recognize "turn on the air conditioner".
In a specific embodiment, the step S102 further includes:
if the voice text is successfully identified, generating a task instruction and a broadcast instruction according to the searched corpus corresponding to the voice text, wherein the task instruction is used for controlling the execution unit to execute a corresponding task, and the broadcast instruction is used for controlling the broadcast unit to broadcast the content corresponding to the corpus.
Specifically, for example, a user sends a voice instruction of "opening an air conditioner" in a vehicle-mounted scene, and the corpus of "opening the air conditioner" is stored, so that the "opening the air conditioner" can be recognized, a task instruction of "opening the air conditioner" and a broadcast instruction are generated, the air conditioner starts to operate after receiving the task instruction, the broadcast unit broadcasts "opening the air conditioner" or "the air conditioner is being opened" after receiving the broadcast instruction, and the like, and specific broadcast contents can be preset and are not necessarily the same as the voice instruction.
It should be noted that, when a speech text is recognized, an intention of the speech text may be obtained, the intention of the speech text corresponds to a corpus, and generating a task instruction according to the corpus in this document may be specifically understood as generating a task instruction corresponding to the intention.
In a specific embodiment, the step S103 includes:
step S201, after outputting the first prompt message, receiving a teaching ending voice instruction input by a user within a preset time;
step S202, when a teaching end voice instruction input by a user is received, task operation information in a time period from the time when the first prompt information is output to the time when the teaching end voice instruction is input by the user is acquired;
step S203, obtaining a plurality of default corpora corresponding to the task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus.
Step S103 of the present embodiment will be specifically described below by taking two cases:
in an example, for example, the "problem i do not understand, please teach me" is broadcasted in a voice manner, after the user hears the broadcast, the user operates the corresponding execution unit within a preset time, taking "open cold air" as an example, the user opens the air conditioner within the preset time, after the operation is finished, a teaching end voice instruction is input, for example, the teaching end voice instruction is "teaching end", for example, "i teach over", for example, and specifically, the setting can be performed according to the usage habit of the user. When a teaching end voice command input by a user is received, which indicates that the teaching of the user is finished, if the time for outputting the first prompt information is T1 and the time for receiving the teaching end voice command input by the user is T2, task operation information of the user on an execution unit in a time period from T1 to T2 is acquired, and an air conditioner is turned on under the manual operation of the user in the time period from T1 to T2, namely the task operation information corresponds to the turning on of the air conditioner; and if the default language material is 'open air conditioner', establishing a language material relationship between the default language material 'open air conditioner' and the voice text 'open air conditioner', namely 'open air conditioner' is equal to 'open air conditioner', and finally storing the 'open air conditioner' as a new language material and the relationship between the language material 'open air conditioner' and the language material 'open air conditioner' in a language material base.
Specifically, after the user defines the voice command of "open air conditioning", and after the user sends the voice command of "open air conditioning" again, because the corpus of the "open air conditioning" and the relation between the corpus of the "open air conditioning" and other corpora of the "open air conditioning" are already stored in the corpus, the NPL engine can recognize the voice text of the "open air conditioning", retrieve the corpus of the corpora of the "open air conditioning", the corpus of the "open air conditioning", and the relation between the "open air conditioning" and other corpora of the "open air conditioning", and then generate a task command of opening the air conditioning and a corresponding broadcast command according to the corpus "open air conditioning".
In the example, the user adopts a single behavior action mode to carry out the intention teaching of the linguistic data, an accurate, direct, quick and simple mode is adopted to carry out the field and intention recognition of the voice instruction, the newly added linguistic data and the original default linguistic data corresponding to the behavior action are bound and correspond, after the linguistic data is newly added, the system inputs the voice text which is not completely consistent in subsequent operation, and the non-default linguistic data (the dynamic linguistic data defined by the user) can be effectively recognized according to the linguistic data relation of the linguistic data.
In another example, for example, the "problem i do not understand, please teach me" is broadcasted in a voice manner, after the user hears the broadcast, the user operates the corresponding execution unit within a preset time, taking "weather is hot", for example, the user opens the air conditioner and closes the window within the preset time, after the operation is finished, the teaching finishing voice instruction is input, and the teaching finishing voice instruction is, for example, "teaching finishing", and specifically may be set according to the usage of the user. When a teaching end voice command input by a user is received, the teaching of the user is finished, if the time for outputting the first prompt information is T1, and the time for receiving the teaching end voice command input by the user is T2, task operation information of the user on an execution unit in a time period from T1 to T2 is acquired, an air conditioner is opened under the manual operation of the user in the time period from T1 to T2, a window is closed under the manual operation of the user, namely the task operation information corresponds to the opening of the air conditioner and the closing of the window; and then the default corpora are 'air conditioner on' and 'window off', establishing a corpus relationship between the default corpora 'air conditioner on' and 'window off' and the voice text 'weather good hot', namely 'weather good hot' is equal to 'air conditioner on' and 'window off', and finally storing the 'weather good hot' as a new corpus and the relationship between the corpus 'weather good hot' and the corpora 'air conditioner on' and the corpus 'window off' in the corpus.
Specifically, after the user self-defines the voice command of the weather good hot, after the user sends the voice command of the weather good hot again, because the linguistic data of the weather good hot and the relation between the linguistic data of the weather good hot and the linguistic data of other linguistic data of opening the air conditioner and closing the window are already stored in the linguistic database, the NPL engine can recognize the voice text of the weather good hot, retrieve the linguistic data of the weather good hot, the linguistic data of opening the air conditioner and closing the window, and the linguistic data relation that the weather good hot is equal to the linguistic data relation between opening the air conditioner and closing the window, and then generate a task command of opening the air conditioner, a task command of closing the window and a corresponding broadcasting command according to the linguistic data of opening the air conditioner and closing the window.
In the example, the user adopts a mode of a plurality of behavior actions to carry out the intention teaching of the corpus, and adopts an accurate, direct, quick and simple mode to carry out the field and intention recognition of the voice command.
In an embodiment, the step S203 specifically includes:
s301, acquiring a plurality of default corpora corresponding to the task operation information; the task operation information comprises operation information of a plurality of tasks, and each task corresponds to a default corpus;
specifically, for example, the task operation information includes two tasks of opening the air conditioner and closing the window, and corresponds to the default corpora "open the air conditioner" and "close the window", respectively.
Step S302, outputting second prompt information according to the default corpora, wherein the second prompt information is used for requesting a user to confirm whether the default corpora are consistent with the voice text;
specifically, taking the input voice command as "weather hot and warm" as an example, the second prompt message may be "whether the weather hot and warm is the meaning of opening the air conditioner and closing the window".
Step S303, after the second prompt message is output, if the confirmation message input by the user is received, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus.
Specifically, the prompting mode of the first prompting message may be a voice mode and/or a mode of displaying by a display unit. After getting the prompt of the second prompt information, the user inputs confirmation information through the voice input unit or the physical input unit, for example, issues a voice instruction "yes". And after receiving confirmation information input by a user, establishing a corpus relation between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relation into a corpus.
In a specific embodiment, the method further comprises:
step S401, determining a task corresponding to each corpus according to a plurality of corpora of the corpus and a corpus relation between the corpora;
step S402, generating display information according to the task corresponding to each corpus, and sending the display information to a display unit; the display unit is used for displaying the display information.
Specifically, the display of the corpus and the corresponding tasks is provided in the embodiment, so that the user can conveniently view the corpus and the corresponding tasks. In the application process, a user may input a viewing request message through a voice mode or through a physical input unit, and after the viewing request message is acquired, the steps S401 to S402 are executed, and specifically, the viewing request message may be displayed through a display unit of the vehicle-mounted terminal.
In a specific embodiment, the method further comprises:
step S501, obtaining corpus modification information or corpus deletion information input by a user;
step S502, the corpus and/or the corpus relation in the corpus is modified according to the corpus modification information, or the corpus and/or the corpus relation in the corpus is deleted according to the corpus deletion information.
Specifically, the corpus modification information may be to modify words of a corpus or a corpus relationship between corpuses of a corpus, and the corpus deletion information may be to delete a corpus relationship between words of a corpus or between corpuses of a corpus, so that a user may delete an instruction in a corpus. In the application process, the display unit of the vehicle-mounted terminal displays the corpus and the corresponding task thereof, the user can input corpus modification information or corpus deletion information in a voice mode or through a physical input unit, and the step S501-the step S502 are executed after the corpus modification information or the corpus deletion information is obtained.
Another embodiment of the present invention provides a corpus updating system, which can be used to implement the corpus updating method in the foregoing embodiments, and fig. 2 is a block diagram of the system in this embodiment, referring to fig. 2, the system in this embodiment includes:
the information acquisition unit 1 is used for acquiring a voice instruction input by a user and acquiring a voice text according to the voice instruction;
the recognition processing unit 2 is used for recognizing the voice text, and if the voice text cannot be recognized, outputting first prompt information for requesting a user to perform action teaching; and
the corpus updating unit 3 is configured to acquire a plurality of default corpuses corresponding to the task operation information, establish a corpus relationship between the plurality of default corpuses and the voice text, and store the voice text as a new corpus and the corpus relationship into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time.
In a specific embodiment, the identification processing unit 2 specifically includes:
a text recognition unit 21 configured to recognize the speech text; specifically, searching whether a corpus exists corresponding to the voice text or not, if the corpus exists corresponding to the voice text, the recognition is successful, and if the corpus does not exist, the recognition cannot be performed;
a teaching prompt unit 22, configured to output first prompt information requesting a user to perform action teaching if the speech text cannot be recognized; and
and the task instruction generating unit 23 is configured to generate a task instruction and a broadcast instruction according to the corpus corresponding to the voice text in the retrieved corpus if the voice text is successfully identified, where the task instruction is used to control the execution unit to execute a corresponding task, and the broadcast instruction is used to control the broadcast unit to broadcast the content corresponding to the corpus.
In an embodiment, the corpus updating unit 3 includes:
the first updating processing unit 31 is configured to receive a teaching end voice instruction input by a user within a preset time after the first prompt information is output;
the second update processing unit 32 is configured to, when a teaching end voice instruction input by a user is received, acquire task operation information in a time period from when the first prompt information is output to when the teaching end voice instruction is input by the user; and
the third update processing unit 33 is configured to acquire a plurality of default corpora corresponding to the task operation information, establish a corpus relationship between the default corpora and the voice text, and store the voice text as a new corpus and the corpus relationship into the corpus.
In an embodiment, the third update processing unit 33 includes:
the default corpus acquiring unit is used for acquiring a plurality of default corpora corresponding to the task operation information; the task operation information comprises operation information of a plurality of tasks, and each task corresponds to a default corpus;
the corpus confirmation prompting unit is used for outputting second prompting information according to the default corpuses, and the second prompting information is used for requesting a user to confirm whether the default corpuses are consistent with the voice text; and
and the corpus increasing unit is used for establishing a corpus relation between the default corpora and the voice text after the second prompt information is output and if confirmation information input by a user is received, and storing the voice text serving as a new corpus and the corpus relation into a corpus.
In a specific embodiment, the system further comprises:
the determining unit is used for determining a task corresponding to each corpus according to the corpus relations among the corpora and the corpora of the corpus;
the display information generating unit is used for generating display information according to the task corresponding to each corpus and sending the display information to the display unit; the display unit is used for displaying the display information.
In a specific embodiment, the system further comprises:
a deletion information acquisition unit for acquiring corpus modification information or corpus deletion information input by a user;
and the deleting processing unit is used for modifying the corpus and/or the corpus relation in the corpus according to the corpus modification information, or deleting the corpus and/or the corpus relation in the corpus according to the corpus deletion information.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
It should be noted that the system described in the foregoing embodiment corresponds to the method described in the foregoing embodiment, and therefore, portions of the system described in the foregoing embodiment that are not described in detail can be obtained by referring to the content of the method described in the foregoing embodiment, and details are not described here.
Moreover, the corpus updating system according to the above embodiment may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a stand-alone product.
The embodiment of the invention also provides voice control equipment, which comprises the corpus updating system in the embodiment; or a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the method for updating according to the corpus described above.
Of course, the voice control device may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the voice control device may also include other components for implementing the functions of the device, which are not described herein again.
Illustratively, the computer program may be divided into one or more units, which are stored in the memory and executed by the processor to accomplish the present invention. The one or more units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the voice control device.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center for the voice control device, with various interfaces and lines connecting the various parts of the overall voice control device.
The memory may be used to store the computer program and/or unit, and the processor may implement the various functions of the voice control apparatus by running or executing the computer program and/or unit stored in the memory, and calling data stored in the memory. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (11)
1. A corpus update method, comprising:
step S1, acquiring a voice instruction input by a user, and acquiring a voice text according to the voice instruction;
step S2, recognizing the voice text, and if the voice text cannot be recognized, outputting first prompt information for requesting a user to perform action teaching;
step S3, acquiring a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time.
2. A corpus updating method according to claim 1, wherein said step S2 includes:
searching whether a corpus exists corresponding to the voice text or not, if so, successfully identifying, and if not, failing to identify;
if the voice text is successfully identified, generating a task instruction and a broadcast instruction according to the searched corpus corresponding to the voice text, wherein the task instruction is used for controlling the execution unit to execute a corresponding task, and the broadcast instruction is used for controlling the broadcast unit to broadcast the content corresponding to the corpus.
3. A corpus updating method according to claim 1, wherein said step S3 includes:
after the first prompt message is output, receiving a teaching ending voice command input by a user within preset time;
when a teaching end voice instruction input by a user is received, acquiring task operation information in a time period from the time when the first prompt information is output to the time when the teaching end voice instruction is input by the user;
acquiring a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus.
4. The method for corpus updating according to claim 3, wherein obtaining a plurality of default corpora corresponding to task operation information, establishing a corpus relationship between the default corpora and the speech text, and storing the speech text as a new corpus and the corpus relationship into a corpus, specifically comprises:
acquiring a plurality of default corpora corresponding to the task operation information; the task operation information comprises operation information of a plurality of tasks, and each task corresponds to a default corpus;
outputting second prompt information according to the default corpora, wherein the second prompt information is used for requesting a user to confirm whether the default corpora are consistent with the voice text;
after the second prompt message is output, if confirmation information input by a user is received, establishing a corpus relationship between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relationship into a corpus.
5. The voice control method of claim 1, further comprising:
determining a task corresponding to each corpus according to a plurality of corpora of the corpus and a corpus relation between the corpora;
generating display information according to the task corresponding to each corpus, and sending the display information to a display unit; the display unit is used for displaying the display information.
6. The voice control method of claim 5, further comprising:
obtaining corpus modification information or corpus deletion information input by a user;
and modifying the corpus and/or the corpus relation in the corpus according to the corpus modification information, or deleting the corpus and/or the corpus relation in the corpus according to the corpus deletion information.
7. A corpus update system, comprising:
the information acquisition unit is used for acquiring a voice instruction input by a user and acquiring a voice text according to the voice instruction;
the recognition processing unit is used for recognizing the voice text, and if the voice text cannot be recognized, outputting first prompt information for requesting a user to perform action teaching; and
the corpus updating unit is used for acquiring a plurality of default corpuses corresponding to the task operation information, establishing a corpus relation between the default corpuses and the voice text, and storing the voice text as a new corpus and the corpus relation into a corpus; and after the first prompt message is output, the user operates the execution unit to execute the corresponding task within the preset time.
8. A corpus updating system as claimed in claim 7, wherein the corpus updating unit includes:
the first updating processing unit is used for receiving a teaching ending voice instruction input by a user within preset time after outputting the first prompt message;
the second updating processing unit is used for acquiring task operation information in a time period from the time when the first prompt information is output to the time when the teaching ending voice instruction input by the user is received; and
and the third updating processing unit is used for acquiring a plurality of default corpora corresponding to the task operation information, establishing a corpus relation between the default corpora and the voice text, and storing the voice text as a new corpus and the corpus relation into a corpus.
9. Corpus update system according to claim 8, wherein said third update processing unit includes:
the default corpus acquiring unit is used for acquiring a plurality of default corpora corresponding to the task operation information; the task operation information comprises operation information of a plurality of tasks, and each task corresponds to a default corpus;
the corpus confirmation prompting unit is used for outputting second prompting information according to the default corpuses, and the second prompting information is used for requesting a user to confirm whether the default corpuses are consistent with the voice text; and
and the corpus increasing unit is used for establishing a corpus relation between the default corpora and the voice text after the second prompt information is output and if confirmation information input by a user is received, and storing the voice text serving as a new corpus and the corpus relation into a corpus.
10. The voice control system of claim 7, further comprising:
the determining unit is used for determining a task corresponding to each corpus according to the corpus relations among the corpora and the corpora of the corpus;
the display information generating unit is used for generating display information according to the task corresponding to each corpus and sending the display information to the display unit; the display unit is used for displaying the display information;
a deletion information acquisition unit for acquiring corpus modification information or corpus deletion information input by a user;
and the deleting processing unit is used for modifying the corpus and/or the corpus relation in the corpus according to the corpus modification information, or deleting the corpus and/or the corpus relation in the corpus according to the corpus deletion information.
11. A voice-controlled device comprising: a corpus update system according to any one of claims 7-10; or a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of the corpus update method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010073090.2A CN113160807A (en) | 2020-01-22 | 2020-01-22 | Corpus updating method and system and voice control equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010073090.2A CN113160807A (en) | 2020-01-22 | 2020-01-22 | Corpus updating method and system and voice control equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113160807A true CN113160807A (en) | 2021-07-23 |
Family
ID=76881696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010073090.2A Pending CN113160807A (en) | 2020-01-22 | 2020-01-22 | Corpus updating method and system and voice control equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113160807A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113909743A (en) * | 2021-09-30 | 2022-01-11 | 北京博清科技有限公司 | Welding control method, control device and welding system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1935065A (en) * | 2005-09-19 | 2007-03-28 | 刘小勇 | Cooking prompting method and device |
| CN101013635A (en) * | 2006-12-13 | 2007-08-08 | 淄博微联电子有限公司 | Intelligent remote control locking method and apparatus for preventing electric misoperation |
| CN105679315A (en) * | 2016-03-22 | 2016-06-15 | 谢奇 | Voice-activated and voice-programmed control method and control system |
| CN106156022A (en) * | 2015-03-23 | 2016-11-23 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN107195300A (en) * | 2017-05-15 | 2017-09-22 | 珠海格力电器股份有限公司 | Sound control method and system |
| CN108831469A (en) * | 2018-08-06 | 2018-11-16 | 珠海格力电器股份有限公司 | Voice command method for customizing, device and equipment and computer storage medium |
| CN110570867A (en) * | 2019-09-12 | 2019-12-13 | 安信通科技（澳门）有限公司 | Voice processing method and system for locally added corpus |
-
2020
- 2020-01-22 CN CN202010073090.2A patent/CN113160807A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1935065A (en) * | 2005-09-19 | 2007-03-28 | 刘小勇 | Cooking prompting method and device |
| CN101013635A (en) * | 2006-12-13 | 2007-08-08 | 淄博微联电子有限公司 | Intelligent remote control locking method and apparatus for preventing electric misoperation |
| CN106156022A (en) * | 2015-03-23 | 2016-11-23 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN105679315A (en) * | 2016-03-22 | 2016-06-15 | 谢奇 | Voice-activated and voice-programmed control method and control system |
| CN107195300A (en) * | 2017-05-15 | 2017-09-22 | 珠海格力电器股份有限公司 | Sound control method and system |
| CN108831469A (en) * | 2018-08-06 | 2018-11-16 | 珠海格力电器股份有限公司 | Voice command method for customizing, device and equipment and computer storage medium |
| CN110570867A (en) * | 2019-09-12 | 2019-12-13 | 安信通科技（澳门）有限公司 | Voice processing method and system for locally added corpus |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113909743A (en) * | 2021-09-30 | 2022-01-11 | 北京博清科技有限公司 | Welding control method, control device and welding system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108831469B (en) | Voice command customizing method, device and equipment and computer storage medium | |
| CN106098063B (en) | Voice control method, terminal device and server | |
| CN109979450B (en) | Information processing method and device and electronic equipment | |
| CN112017646A (en) | Voice processing method and device and computer storage medium | |
| CN112149419B (en) | Method, device and system for normalized automatic naming of fields | |
| CN110691160A (en) | Voice control method and device and mobile phone | |
| KR20220052581A (en) | Method and system for providing search results incorporating the intent of search query | |
| CN109064787B (en) | Point reading equipment | |
| CN109326284A (en) | The method, apparatus and storage medium of phonetic search | |
| CN112346697A (en) | Method, device and storage medium for controlling equipment | |
| CN112004145A (en) | Program advertisement skipping processing method and device, television and system | |
| CN113160807A (en) | Corpus updating method and system and voice control equipment | |
| CN110797012A (en) | Information extraction method, equipment and storage medium | |
| CN111063337B (en) | Large-scale voice recognition method and system capable of rapidly updating language model | |
| CN112151034A (en) | Voice control method and device of equipment, electronic equipment and storage medium | |
| US11726656B2 (en) | Intelligent keyboard | |
| CN112114770A (en) | Interface guiding method, device and equipment based on voice interaction | |
| CN112533007B (en) | Network live broadcast method, system, terminal device and storage medium | |
| US7822614B2 (en) | Device control, speech recognition device, agent device, control method | |
| CN112380871A (en) | Semantic recognition method, apparatus, and medium | |
| CN110895924B (en) | Method and device for reading document content aloud, electronic equipment and readable storage medium | |
| CN113241067B (en) | Voice interaction method and system and voice interaction equipment | |
| CN113160808A (en) | Voice control method and system and voice control equipment | |
| CN113470636B (en) | Voice information processing method, device, equipment and medium | |
| CN111753046A (en) | Method and apparatus for controlling smart device, electronic device, and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |